Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105158
    Prev
    Next
    INDEX
    Explanations

    expressions of negative or challenging personal experiences.

    oai_token-act-pair · gpt-4oTriggered by @joshengels

    expressions of struggle, disappointment, and interpersonal conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.65
    原始内容存档于
    -0.65
     createState
    -0.63
    Derbyniad
    -0.59
     chofe
    -0.59
    XmlAccessorType
    -0.59
    enderror
    -0.59
     مشين
    -0.57
    hyrchwyd
    -0.56
     nakalista
    -0.56
    POSITIVE LOGITS
     afectar
    0.35
     Due
    0.32
    +#+
    0.29
     vuel
    0.29
     Far
    0.29
     Mut
    0.29
     suspendu
    0.29
     Fer
    0.28
     audiencia
    0.28
    stre
    0.28
    Activations Density 0.104%

    No Known Activations